Voleon·Software Engineer·Onsite - Multi Round
- Explain the power method for finding leading eigenvectors and walk through its convergence properties.
- Why does adding a sparsity constraint to PCA make the eigenvector problem fundamentally harder to solve?
- Walk through the bias-variance trade-off across different model families: linear regression, ridge, lasso, kernel methods, and tree ensembles. When does each tend to minimize total error?
- Solve a geometric interpretation problem involving linear regression, specifically around projections and orthogonal complements.
“I knew the algorithm itself fine but the convergence explanation got shaky.”